CYAIMAMar 11, 2019

Blameworthiness in Multi-Agent Settings

arXiv:1903.04102v130 citations
Originality Incremental advance
AI Analysis

This work addresses the challenge of moral behavior in autonomous agents, but it appears incremental as it builds on existing concepts like causal models and cooperative game theory without introducing a new paradigm.

The paper tackles the problem of defining blameworthiness in multi-agent scenarios where agents could collaborate to prevent negative outcomes, by proposing a formal method to assign blame to groups and individuals using causal models and the Shapley value.

We provide a formal definition of blameworthiness in settings where multiple agents can collaborate to avoid a negative outcome. We first provide a method for ascribing blameworthiness to groups relative to an epistemic state (a distribution over causal models that describe how the outcome might arise). We then show how we can go from an ascription of blameworthiness for groups to an ascription of blameworthiness for individuals using a standard notion from cooperative game theory, the Shapley value. We believe that getting a good notion of blameworthiness in a group setting will be critical for designing autonomous agents that behave in a moral manner.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes